From: Moshe Shemesh <moshe@nvidia.com>

The health poll mechanism performs periodic checks to detect firmware
errors. One of the checks verifies the function is still enabled on
firmware side, but the function is enabled only after enable_hca command
completed. Start health poll after enable_hca command to avoid a race
between function enabled and first health polling.

Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ec956c4bcebd..7c3312d6aed9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1205,24 +1205,24 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
 
-	mlx5_start_health_poll(dev);
-
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
-		goto stop_health_poll;
+		goto err_cmd_cleanup;
 	}
 
+	mlx5_start_health_poll(dev);
+
 	err = mlx5_core_set_issi(dev);
 	if (err) {
 		mlx5_core_err(dev, "failed to set issi\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 1);
 	if (err) {
 		mlx5_core_err(dev, "failed to allocate boot pages\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_tout_query_dtor(dev);
@@ -1235,10 +1235,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 
 reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
-err_disable_hca:
-	mlx5_core_disable_hca(dev, 0);
 stop_health_poll:
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
@@ -1249,8 +1248,8 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot)
 {
 	mlx5_reclaim_startup_pages(dev);
-	mlx5_core_disable_hca(dev, 0);
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
 }
-- 
2.31.1

On Wed, Mar 19, 2025 at 2:22 AM Tariq Toukan <tariqt@nvidia.com> wrote:
>
> From: Moshe Shemesh <moshe@nvidia.com>
>
> The health poll mechanism performs periodic checks to detect firmware
> errors. One of the checks verifies the function is still enabled on
> firmware side, but the function is enabled only after enable_hca command
> completed. Start health poll after enable_hca command to avoid a race
> between function enabled and first health polling.
>
> Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load")
> Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
> Reviewed-by: Shay Drori <shayd@nvidia.com>
> Signed-off-by: Tariq Toukan <tariqt@nvidia.com>

Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
-- 
Regards,
Kalesh AP

On Tue, Mar 18, 2025 at 10:51:17PM +0200, Tariq Toukan wrote:
> From: Moshe Shemesh <moshe@nvidia.com>
> 
> The health poll mechanism performs periodic checks to detect firmware
> errors. One of the checks verifies the function is still enabled on
> firmware side, but the function is enabled only after enable_hca command
> completed. Start health poll after enable_hca command to avoid a race
> between function enabled and first health polling.
> 
> Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load")
> Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
> Reviewed-by: Shay Drori <shayd@nvidia.com>
> Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
> ---
>  drivers/net/ethernet/mellanox/mlx5/core/main.c | 15 +++++++--------
>  1 file changed, 7 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
> index ec956c4bcebd..7c3312d6aed9 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
> @@ -1205,24 +1205,24 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
>  	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
>  	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
>  
> -	mlx5_start_health_poll(dev);
> -
>  	err = mlx5_core_enable_hca(dev, 0);
>  	if (err) {
>  		mlx5_core_err(dev, "enable hca failed\n");
> -		goto stop_health_poll;
> +		goto err_cmd_cleanup;
>  	}
>  
> +	mlx5_start_health_poll(dev);
> +
>  	err = mlx5_core_set_issi(dev);
>  	if (err) {
>  		mlx5_core_err(dev, "failed to set issi\n");
> -		goto err_disable_hca;
> +		goto stop_health_poll;
>  	}
>  
>  	err = mlx5_satisfy_startup_pages(dev, 1);
>  	if (err) {
>  		mlx5_core_err(dev, "failed to allocate boot pages\n");
> -		goto err_disable_hca;
> +		goto stop_health_poll;
>  	}
>  
>  	err = mlx5_tout_query_dtor(dev);
> @@ -1235,10 +1235,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
>  
>  reclaim_boot_pages:
>  	mlx5_reclaim_startup_pages(dev);
> -err_disable_hca:
> -	mlx5_core_disable_hca(dev, 0);
>  stop_health_poll:
>  	mlx5_stop_health_poll(dev, boot);
> +	mlx5_core_disable_hca(dev, 0);
>  err_cmd_cleanup:
>  	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
>  	mlx5_cmd_disable(dev);
> @@ -1249,8 +1248,8 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
>  static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot)
>  {
>  	mlx5_reclaim_startup_pages(dev);
> -	mlx5_core_disable_hca(dev, 0);
>  	mlx5_stop_health_poll(dev, boot);
> +	mlx5_core_disable_hca(dev, 0);
>  	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
>  	mlx5_cmd_disable(dev);
>  }

Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>

> -- 
> 2.31.1